Advanced Search
Volume 45 Issue 3
Mar.  2023
Turn off MathJax
Article Contents
ZHOU Jin, LI Yuzhi, LI Bin. Image Processing-Driven Spectrum Sensing with Small Training Samples[J]. Journal of Electronics & Information Technology, 2023, 45(3): 1102-1110. doi: 10.11999/JEIT220084
Citation: ZHOU Jin, LI Yuzhi, LI Bin. Image Processing-Driven Spectrum Sensing with Small Training Samples[J]. Journal of Electronics & Information Technology, 2023, 45(3): 1102-1110. doi: 10.11999/JEIT220084

Image Processing-Driven Spectrum Sensing with Small Training Samples

doi: 10.11999/JEIT220084
Funds:  The Humanities and Social Sciences of Ministry of Education Planning fund (19YJA630046), Tianjin Education Commission Scientific Research Program (2021SK102)
  • Received Date: 2022-01-19
  • Accepted Date: 2022-08-25
  • Rev Recd Date: 2022-08-24
  • Available Online: 2022-08-30
  • Publish Date: 2023-03-10
  • To resolve the problems of high computational complexity in strong noise environment, infeasibility of gaining large number of labeled samples and low detection probability, an Image Denoising and Classification driven Spectrum Sensing (IDCSS) method is proposed. Firstly, time-frequency transformation is employed to convert radio numerical signals into images. Then, as received signals of cognitive users and noise are highly correlated under strong noise environments, a novel Generative Adversarial Network (GAN) is designed to enhance the number and quality of samples of cognitive user signals. In the generator, residual-long-short-term memory network is designed to replace U-Net skip connection, realizing denoising and multi-scale features extraction. Loss function based on entropy is designed to optimize robustness to noise. A multi-dimensional discriminator is designed to enhance the quality of the generated image and retain the image details of the low signal-to-noise ratio cognitive user signals. Finally, the generated high-quality samples are used as labeled data, and the real samples combine to train the classifier to realize the recognition and classification of the spectrum occupancy state. Simulation results show that the proposed algorithm has better detection performance by comparing it with the state-of-the-art methods.
  • loading
  • [1]
    陈勇, 张余, 柳永祥. 电磁频谱战发展剖析与思考[J]. 指挥与控制学报, 2018, 4(4): 319–324.

    CHEN Yong, ZHANG Yu, and LIU Yongxiang. Analysis and thinking on the development of electromagnetic spectrum warfare[J]. Journal of Command and Control, 2018, 4(4): 319–324.
    [2]
    XIONG Tianyi, YAO Yudong, REN Yujue, et al. Multiband spectrum sensing in cognitive radio networks with secondary user hardware limitation: Random and adaptive spectrum sensing strategies[J]. IEEE Transactions on Wireless Communications, 2018, 17(5): 3018–3029. doi: 10.1109/TWC.2018.2805729
    [3]
    张莹, 滕伟, 韩维佳, 等. 认知无线电频谱感知技术综述[J]. 无线电通信技术, 2015, 41(3): 12–16. doi: 10.3969/j.issn.1673-1131.2015.07.056

    ZHANG Ying, TENG Wei, HAN Weijia, et al. Review of spectrum sensing techniques in cognitive radio networks[J]. Radio Communications Technology, 2015, 41(3): 12–16. doi: 10.3969/j.issn.1673-1131.2015.07.056
    [4]
    CHEN Hongsong, ZHANG Yongpeng, CAO Yongrui, et al. Security issues and defensive approaches in deep learning frameworks[J]. Tsinghua Science and Technology, 2021, 26(6): 894–905. doi: 10.26599/TST.2020.9010050
    [5]
    TANG Hao, LIU Hong, XIAO Wei, et al. When dictionary learning meets deep learning: Deep dictionary learning and coding network for image recognition with limited data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(5): 2129–2141. doi: 10.1109/TNNLS.2020.2997289
    [6]
    WANG Xi, TANG Fangyao, CHEN Hao, et al. UD-MIL: Uncertainty-driven deep multiple instance learning for OCT image classification[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(12): 3431–3442. doi: 10.1109/JBHI.2020.2983730
    [7]
    盖建新, 薛宪峰, 吴静谊, 等. 基于深度卷积神经网络的协作频谱感知方法[J]. 电子与信息学报, 2021, 43(10): 2911–2919. doi: 10.11999/JEIT201005

    GAI Jianxin, XUE Xianfeng, WU Jingyi, et al. Cooperative spectrum sensing method based on deep convolutional neural network[J]. Journal of Electronics &Information Technology, 2021, 43(10): 2911–2919. doi: 10.11999/JEIT201005
    [8]
    岳文静, 刘文博, 陈志. 基于图像K-means聚类分析的频谱感知算法[J]. 信号处理, 2020, 36(2): 203–209. doi: 10.16798/j.issn.1003-0530.2020.02.006

    YUE Wenjing, LIU Wenbo, and CHEN Zhi. Spectrum sensing algorithm based on image K-means clustering analysis[J]. Journal of Signal Processing, 2020, 36(2): 203–209. doi: 10.16798/j.issn.1003-0530.2020.02.006
    [9]
    DAVASLIOGLU K and SAGDUYU Y E. Generative adversarial learning for spectrum sensing[C]. 2018 IEEE International Conference on Communications, Kansas City, USA, 2018: 1–6.
    [10]
    LIU Zheng, JING Xiaojun, ZHANG Ronghui, et al. Spectrum sensing based on deep convolutional generative adversarial networks[C]. 2021 International Wireless Communications and Mobile Computing, Harbin, China, 2021: 796–801.
    [11]
    MAO Xudong, LI Qing, XIE Haoran, et al. Least squares generative adversarial networks[C]. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017: 2813–2821.
    [12]
    麻文刚, 张亚东, 郭进. 基于LSTM与改进残差网络优化的异常流量检测方法[J]. 通信学报, 2021, 42(5): 23–40. doi: 10.11959/j.issn.1000-436x.2021109

    MA Wengang, ZHANG Yadong, and GUO Jin. Abnormal traffic detection method based on LSTM and improved residual neural network optimization[J]. Journal on Communications, 2021, 42(5): 23–40. doi: 10.11959/j.issn.1000-436x.2021109
    [13]
    蒲悦逸, 王文涵, 朱强, 等. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9–14. doi: 10.13190/j.jbupt.2019-243

    PU Yueyi, WANG Wenhan, ZHU Qiang, et al. Urban short-term traffic flow prediction algorithm based on CNN-ResNet-LSTM model[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 9–14. doi: 10.13190/j.jbupt.2019-243
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(12)  / Tables(4)

    Article Metrics

    Article views (495) PDF downloads(79) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return